Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.9632. Min Act: -0.1700
Data Index: 3718987 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.9632. Min Act: -0.1700
Data Index: 213382 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.9319. Min Act: -0.1700
Data Index: 5122021 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.9632. Min Act: -0.1700
Data Index: 1339908 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8694. Min Act: -0.1700
Data Index: 7815499 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.9006. Min Act: -0.1700
Data Index: 3223669 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8694. Min Act: -0.1700
Data Index: 3247995 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8381. Min Act: -0.1700
Data Index: 1548826 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8381. Min Act: -0.1700
Data Index: 4681617 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8381. Min Act: -0.1700
Data Index: 7013059 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8381. Min Act: -0.1700
Data Index: 2867737 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8068. Min Act: -0.1700
Data Index: 3122275 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8068. Min Act: -0.1700
Data Index: 3227970 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8068. Min Act: -0.1700
Data Index: 1848233 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7756. Min Act: -0.1700
Data Index: 8561173 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7756. Min Act: -0.1700
Data Index: 7814944 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7443. Min Act: -0.1700
Data Index: 3055 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7443. Min Act: -0.1700
Data Index: 4802679 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7443. Min Act: -0.1700
Data Index: 5437308 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7443. Min Act: -0.1700
Data Index: 6015845 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19